From: aaronshaw Date: Thu, 2 Apr 2020 12:49:08 +0000 (-0500) Subject: removing outdated file names X-Git-Url: https://code.communitydata.science/covid19.git/commitdiff_plain/4ab432f399c9024774b6de58fbf6c1c2b7f2e122?ds=inline removing outdated file names --- diff --git a/wikipedia/analysis/output/top10_views_by_project_date.csv b/wikipedia/analysis/output/top10_views_by_project_date.csv deleted file mode 100644 index ce7eb5e..0000000 --- a/wikipedia/analysis/output/top10_views_by_project_date.csv +++ /dev/null @@ -1,11 +0,0 @@ -"article","project","timestamp","views" -"2019–20_coronavirus_pandemic","en.wikipedia","2020033100",831879 -"2020_coronavirus_pandemic_in_India","en.wikipedia","2020033100",323123 -"2019–20_coronavirus_pandemic_by_country_and_territory","en.wikipedia","2020033100",315572 -"2020_coronavirus_pandemic_in_the_United_States","en.wikipedia","2020033100",290535 -"Coronavirus_disease_2019","en.wikipedia","2020033100",211391 -"2020_coronavirus_pandemic_in_Italy","en.wikipedia","2020033100",209908 -"Coronavirus","en.wikipedia","2020033100",188921 -"USNS_Comfort_(T-AH-20)","en.wikipedia","2020033100",150422 -"USNS_Comfort_(T-AH-20)","en.wikipedia","2020033100",150422 -"WrestleMania_36","en.wikipedia","2020033100",137637 diff --git a/wikipedia/analysis/pageview_example.R b/wikipedia/analysis/pageview_example.R deleted file mode 100644 index fb5359a..0000000 --- a/wikipedia/analysis/pageview_example.R +++ /dev/null @@ -1,52 +0,0 @@ -### COVID-19 Digital Observatory -### 2020-03-28 -### -### Minimal example analysis file using pageview data - -library(tidyverse) -library(scales) - -### Import and cleanup one datafile from the observatory - -DataURL <- - url("https://covid19.communitydata.science/datasets/wikipedia/digobs_covid19-wikipedia-enwiki_dailyviews-20200401.tsv") - -views <- - read.table(DataURL, sep="\t", header=TRUE, stringsAsFactors=FALSE) - -### Alternatively, uncomment and run if working locally with full git -### tree -### -### Identify data source directory and file -## DataDir <- ("../data/") -## DataFile <- ("dailyviews2020032600.tsv") - -## related.searches.top <- read.table(paste(DataDir,DataFile, sep=""), -## sep="\t", header=TRUE, -## stringsAsFactors=FALSE) - -### Cleanup and do the grouping with functions from the Tidyverse -### (see https://www.tidyverse.org for more info) - -views <- views[,c("article", "project", "timestamp", "views")] -views$timestamp <- fct_explicit_na(views$timestamp) - - -### Sorts and groups at the same time -views.by.proj.date <- arrange(group_by(views, project, timestamp), - desc(views)) - - -### Export just the top 10 by pageviews -write.table(head(views.by.proj.date, 10), - file="output/top10_views_by_project_date.csv", sep=",", - row.names=FALSE) - -### A simple visualization -p <- ggplot(data=views.by.proj.date, aes(views)) - -## Density plot with log-transformed axis -p + geom_density() + scale_x_log10(labels=comma) - - -